© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94946
    Prev
    Next
    INDEX
    Explanations

    plain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abstractmethod
    -0.58
     sauvage
    -0.56
    AndroidJUnit
    -0.56
    nicamente
    -0.56
    колко
    -0.56
    المناصب
    -0.54
     comigo
    -0.53
     متعلقه
    -0.52
    hime
    -0.52
    gania
    -0.51
    POSITIVE LOGITS
     text
    0.86
    цездатний
    0.64
    text
    0.64
     فريبيس
    0.64
     texte
    0.59
    MathML
    0.57
     texts
    0.56
    文本
    0.53
    texts
    0.53
     sight
    0.51
    Activations Density 0.001%

    No Known Activations